Magnetic Resonance Image Example-Based Contrast Synthesis

Overview

Journal IEEE Trans Med Imaging

Date 2013 Sep 24

PMID 24058022

Citations 49

Authors

Snehashis Roy

Aaron Carass

Jerry L Prince

Affiliations

Soon will be listed here.

Abstract

The performance of image analysis algorithms applied to magnetic resonance images is strongly influenced by the pulse sequences used to acquire the images. Algorithms are typically optimized for a targeted tissue contrast obtained from a particular implementation of a pulse sequence on a specific scanner. There are many practical situations, including multi-institution trials, rapid emergency scans, and scientific use of historical data, where the images are not acquired according to an optimal protocol or the desired tissue contrast is entirely missing. This paper introduces an image restoration technique that recovers images with both the desired tissue contrast and a normalized intensity profile. This is done using patches in the acquired images and an atlas containing patches of the acquired and desired tissue contrasts. The method is an example-based approach relying on sparse reconstruction from image patches. Its performance in demonstrated using several examples, including image intensity normalization, missing tissue contrast recovery, automatic segmentation, and multimodal registration. These examples demonstrate potential practical uses and also illustrate limitations of our approach.

Citing Articles

ReeGAN: MRI image edge-preserving synthesis based on GANs trained with misaligned data.

Lu X, Liang X, Liu W, Miao X, Guan X Med Biol Eng Comput. 2024; 62(6):1851-1868.

PMID: 38396277 DOI: 10.1007/s11517-024-03035-w.

A multimodal deep learning approach for the prediction of cognitive decline and its effectiveness in clinical trials for Alzheimer's disease.

Wang C, Tachimori H, Yamaguchi H, Sekiguchi A, Li Y, Yamashita Y Transl Psychiatry. 2024; 14(1):105.

PMID: 38383536 PMC: 10882004. DOI: 10.1038/s41398-024-02819-w.

Image harmonization improves consistency of intra-rater delineations of MS lesions in heterogeneous MRI.

Carass A, Greenman D, Dewey B, Calabresi P, Prince J, Pham D Neuroimage Rep. 2024; 4(1).

PMID: 38370461 PMC: 10871705. DOI: 10.1016/j.ynirp.2024.100195.

HACA3: A unified approach for multi-site MR image harmonization.

Zuo L, Liu Y, Xue Y, Dewey B, Remedios S, Hays S Comput Med Imaging Graph. 2023; 109:102285.

PMID: 37657151 PMC: 10592042. DOI: 10.1016/j.compmedimag.2023.102285.

One Model to Synthesize Them All: Multi-Contrast Multi-Scale Transformer for Missing Data Imputation.

Liu J, Pasumarthi S, Duffy B, Gong E, Datta K, Zaharchuk G IEEE Trans Med Imaging. 2023; 42(9):2577-2591.

PMID: 37030684 PMC: 10543020. DOI: 10.1109/TMI.2023.3261707.

References

Sabuncu M, Yeo B, Van Leemput K, Fischl B, Golland P . A generative model for image segmentation based on label fusion. IEEE Trans Med Imaging. 2010; 29(10):1714-29. PMC: 3268159. DOI: 10.1109/TMI.2010.2050897. View

Dai Y, Wang Y, Wang L, Wu G, Shi F, Shen D . aBEAT: a toolbox for consistent analysis of longitudinal adult brain MRI. PLoS One. 2013; 8(4):e60344. PMC: 3616755. DOI: 10.1371/journal.pone.0060344. View

Jezzard P, Balaban R . Correction for geometric distortion in echo planar images from B0 field variations. Magn Reson Med. 1995; 34(1):65-73. DOI: 10.1002/mrm.1910340111. View

Nyul L, Udupa J, Zhang X . New variants of a method of MRI scale standardization. IEEE Trans Med Imaging. 2000; 19(2):143-50. DOI: 10.1109/42.836373. View

Clark K, Woods R, Rottenberg D, Toga A, Mazziotta J . Impact of acquisition protocols and processing streams on tissue segmentation of T1 weighted MR images. Neuroimage. 2005; 29(1):185-202. DOI: 10.1016/j.neuroimage.2005.07.035. View

Roy S, Carass A, Bazin P, Resnick S, Prince J . Consistent segmentation using a Rician classifier. Med Image Anal. 2011; 16(2):524-35. PMC: 3267889. DOI: 10.1016/j.media.2011.12.001. View

Avants B, Epstein C, Grossman M, Gee J . Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain. Med Image Anal. 2007; 12(1):26-41. PMC: 2276735. DOI: 10.1016/j.media.2007.06.004. View

Wang L, Lai H, Barker G, Miller D, Tofts P . Correction for variations in MRI scanner sensitivity in brain studies with histogram matching. Magn Reson Med. 1998; 39(2):322-7. DOI: 10.1002/mrm.1910390222. View

Unschuld P, Edden R, Carass A, Liu X, Shanahan M, Wang X . Brain metabolite alterations and cognitive dysfunction in early Huntington's disease. Mov Disord. 2012; 27(7):895-902. PMC: 3383395. DOI: 10.1002/mds.25010. View

10.

Coupe P, Eskildsen S, Manjon J, Fonov V, Collins D . Simultaneous segmentation and grading of anatomical structures for patient's classification: application to Alzheimer's disease. Neuroimage. 2011; 59(4):3736-47. DOI: 10.1016/j.neuroimage.2011.10.080. View

11.

Elad M, Aharon M . Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans Image Process. 2006; 15(12):3736-45. DOI: 10.1109/tip.2006.881969. View

12.

He R, Datta S, Tao G, Narayana P . Information measures-based intensity standardization of MRI. Annu Int Conf IEEE Eng Med Biol Soc. 2009; 2008:2233-6. DOI: 10.1109/IEMBS.2008.4649640. View

13.

Hu S, Coupe P, Pruessner J, Collins D . Nonlocal regularization for active appearance model: Application to medial temporal lobe segmentation. Hum Brain Mapp. 2012; 35(2):377-95. PMC: 6869426. DOI: 10.1002/hbm.22183. View

14.

Eskildsen S, Coupe P, Fonov V, Manjon J, Leung K, Guizard N . BEaST: brain extraction based on nonlocal segmentation technique. Neuroimage. 2011; 59(3):2362-73. DOI: 10.1016/j.neuroimage.2011.09.012. View

15.

Christensen J . Normalization of brain magnetic resonance images using histogram even-order derivative analysis. Magn Reson Imaging. 2003; 21(7):817-20. DOI: 10.1016/s0730-725x(03)00102-4. View

16.

Landman B, Huang A, Gifford A, Vikram D, Lim I, Farrell J . Multi-parametric neuroimaging reproducibility: a 3-T resource study. Neuroimage. 2010; 54(4):2854-66. PMC: 3020263. DOI: 10.1016/j.neuroimage.2010.11.047. View

17.

Rousseau F, Habas P, Studholme C . A supervised patch-based approach for human brain labeling. IEEE Trans Med Imaging. 2011; 30(10):1852-62. PMC: 3318921. DOI: 10.1109/TMI.2011.2156806. View

18.

Roy S, Carass A, Prince J . Synthesizing MR Contrast and Resolution through a Patch Matching Technique. Proc SPIE Int Soc Opt Eng. 2010; 7623:76230j. PMC: 2860803. DOI: 10.1117/12.844575. View

19.

Sled J, Zijdenbos A, Evans A . A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans Med Imaging. 1998; 17(1):87-97. DOI: 10.1109/42.668698. View

20.

Resnick S, Pham D, Kraut M, Zonderman A, Davatzikos C . Longitudinal magnetic resonance imaging studies of older adults: a shrinking brain. J Neurosci. 2003; 23(8):3295-301. PMC: 6742337. View